Partenaires

Logo tutelle
CNRS



Rechercher

Sur ce site

Sur le Web du CNRS


Accueil du site > Séminaires, conférences > Séminaires du LIP > Séminaires en 2008 > Automated systems for the early diagnosis of pathologies : The magic-v project.

Automated systems for the early diagnosis of pathologies : The magic-v project.

Date : 21/11/2008 à 14h00

Intervenants :
- Docteur Sabina TANGARO, Instituto Nazionale di Fisica Nucleare - Sezione di Bari (Italia).

Résumé :

MAGIC-5 Project (Medical Application on a Grid Infrastructure Connection) aims at developing Computer Aided Detection (CADe) software for the analysis of medical images on distributed databases by means of GRID Services. The use of automated systems for analyzing medical images improves radiologists’ performance ; in addition, it could be of paramount importance in screening programs, due to the huge amount of data to check and the cost of related manpower. The need for acquiring and analyzing data stored in different locations requires the use of Grid Services for the management of distributed computing resources and data. The MAGIC-5 project develops algorithms for the analysis of mammographies for breast cancer detection, Computed-Tomography (CT) images for lung cancer detection and Magnetic Resonance Imaging (MRI) images for the early diagnosis of Alzheimer Disease (AD). Mammographic CADe systems. I present a completely automated classification system for the detection of masses in digitized mammographic images. The tool system we discuss consists in three processing levels : a) Image segmentation for the localization of regions of interest (ROIs). This step relies on an iterative dynamical threshold algorithm able to select iso-intensity closed contours around gray level maxima of the mammogram. b) ROI characterization by means of textural features computed from the gray tone spatial dependence matrix (GTSDM). As the images under study were recorded in different centers and with different machine settings, eight GTSDM features were selected so as to be invariant under monotonic transformation. In this way, the images do not need to be normalized, as the adopted features depend on the texture only, rather than on the gray tone levels, too. c) ROI classification by means of a neural network, with supervision provided by the radiologist’s diagnosis. The CAD system was evaluated on a large database of 3369 mammographic images. Lung nodule detection in CT scans A CAD system for the selection of lung nodules in CT images is presented. The CAD consists of three steps : (1) the lung parenchymal volume is segmented by means of a RG algorithm ; the pleural nodules are included through the new active contour model technique ; (2) a RG algorithm is iteratively applied to the previously segmented volume in order to detect the candidate nodules ; (3) a double-threshold cut and a neural network are applied to reduce the false positives. After having set the parameters on a clinical CT, the system works on whole scans, without the need for any manual selection. The CT database was recorded at the Pisa center of the ITALUNG-CT trial, the first Italian randomized controlled trial for the screening of the lung cancer. Development, validation and comparison of algorithms for the analysis of neuroimages The Alzheimer disease (AD) is a progressive, irreversible and degenerative disorder causing disfunction of memory, thinking and behaviour, due to the death of brain cells and connections. This is the most common form of dementia in adult and senior population. In addition the risk to develop the AD raises at increasing age. AD is difficult to diagnose in the early stage ; the first step is known as Mild Cognitive Impairment (MCI), though it is not necessarily a marker of the disease, because MCI subjects can evolve in AD, or in other forms of dementia, or remain stable, or return to a non pathological condition. Many studies have shown that the first region affected by AD is the hippocampus. For this reason, in the present project, the morphological features of the hippocampus have been chosen as markers of the disease.